Differential diagnosis between patients with probable Alzheimer’s disease, Parkinson’s disease dementia, or dementia with Lewy bodies and frontotemporal dementia, behavioral variant, using quantitative electroencephalographic features

Abstract

The objective of this work was to develop and evaluate a classifier for differentiating probable Alzheimer’s disease (AD) from Parkinson’s disease dementia (PDD) or dementia with Lewy bodies (DLB) and from frontotemporal dementia, behavioral variant (bvFTD) based on quantitative electroencephalography (QEEG). We compared 25 QEEG features in 61 dementia patients (20 patients with probable AD, 20 patients with PDD or probable DLB (DLBPD), and 21 patients with bvFTD). Support vector machine classifiers were trained to distinguish among the three groups. Out of the 25 features, 23 turned out to be significantly different between AD and DLBPD, 17 for AD versus bvFTD, and 12 for bvFTD versus DLBPD. Using leave-one-out cross validation, the classification achieved an accuracy, sensitivity, and specificity of 100% using only the QEEG features Granger causality and the ratio of theta and beta1 band powers. These results indicate that classifiers trained with selected QEEG features can provide a valuable input in distinguishing among AD, DLB or PDD, and bvFTD patients. In this study with 61 patients, no misclassifications occurred. Therefore, further studies should investigate the potential of this method to be applied not only on group level but also in diagnostic support for individual subjects.

Abnormalities of resting-state functional cortical connectivity in patients with dementia due to Alzheimer's and Lewy body diseases: an EEG study

“…The first analysis showed significant positive correlations between MMSE scores (roughly reflecting global cognitive status) and LLC solutions in interhemispheric temporal and intrahemispheric diffuse alpha sources across all Nold, ADD, DLB, and PDD individuals as a whole group. However, even if statistically significant (p < 0.005), the correlation values were relatively low as variance explained (2) 0.92-0.78 for MCI vs. ADD individuals; and (3) 0.87-0.60 for the conversion from MCI to ADD status (Adler et al, 2003;Babiloni et al, 2015bBabiloni et al, , 2016bBennys et al, 2001;Blinowska et al, 2017;Brassen et al, 2004;Buscema et al, 2007;Claus et al, 1999;Engedal et al, 2015;Garn et al, 2017;Huang et al, 2000;Jelic et al, 2000;Knyazeva et al, 2010;Lehmann et al, 2007;Lizio et al, 2016;Missonnier et al, 2006;Nuwer, 1997).…”

“…Another recent study in relatively small populations of ADD, PDD/DLB, and frontotemporal dementia patients used 25 discriminant scalp rsEEG power density and functional cortical connectivity (i.e. Granger causality) variables as an input to support vector machine, reaching a classification accuracy of 1.0 (Garn et al, 2017).…”

Revolution of Alzheimer Precision Neurology. Passageway of Systems Biology and Neurophysiology

“…Another study in small populations of ADD, PDD/DLB, and frontotemporal dementia patients reached a classification accuracy of 1.0 using 25 discriminant scalp rsEEG power density and functional cortical connectivity (i.e. Granger causality) variables [375]. In another study, combining quantitative rsEEG variables (including those of functional cortical connectivity) with neuropsychological, clinical, neuroimaging, cerebrospinal fluid, and visual EEG data reached “only” a classification accuracy of 0.87 in the discrimination between ADD, PDD, and DLB persons [376].…”

Alpha event‐related synchronization after eye closing differs in Alzheimer's disease and dementia with Lewy bodies: a magnetoencephalography study

“…Recently, neurophysiological activities have been reported to help in the differential diagnosis among dementias, including DLB . The latest DLB consensus criteria included EEG activities as a supportive biomarker, suggesting the clinical importance of neurophysiological activities in patients with DLB.…”

“…Recently, neurophysiological activities have been reported to help in the differential diagnosis among dementias, including DLB. 29,30 The latest DLB consensus criteria included EEG activities as a supportive biomarker, 31 suggesting the clinical importance of neurophysiological activities in patients with DLB. Our study revealed that DLB patients exhibit a significant reduction in the alpha ERS ratio in the posterior brain regions, including in the inferior temporal gyrus, the left parieto-occipital sulcus, and the right occipital pole, compared to AD patients and healthy individuals.…”